- Data Analysis with Open Source Tools
- Dedication
- SPECIAL OFFER: Upgrade this ebook with O’Reilly
- A Note Regarding Supplemental Files
- Preface
- 1. Introduction
- I. Graphics: Looking at Data
- II. Analytics: Modeling Data
- III. Computation: Mining Data
- IV. Applications: Using Data
- A. Programming Environments for Scientific Computation and Data Analysis
- B. Results from Calculus
- C. Working with Data
- D. About the Author
- Index
- About the Author
- Colophon
- SPECIAL OFFER: Upgrade this ebook with O’Reilly
- Copyright

**AS SOON
AS WE ARE DEALING WITH MORE THAN TWO VARIABLES SIMULTANEOUSLY, THINGS
BECOME MUCH MORE** complicated—in particular,
graphical methods quickly become impractical. In this chapter, I’ll
introduce a number of graphical methods that can be applied to
multivariate problems. All of them work best if the number of variables
is not *too* large (less than 15–25).

The borderline case of *three* variables can be
handled through *false-color plots*, which we will
discuss first.

If the number of variables is greater (but not much greater) than three, then we can construct multiplots from a collection of individual bivariate plots by scanning through the various parameters in a systematic way. This gives rise to scatter-plot matrices and co-plots.

Depicting how an overall entity is composed out of its constituent parts can be a rather nasty problem, especially if the composition changes over time. Because this task is so common, I’ll treat it separately in its own section.

Multi-dimensional visualization continues to be a research topic, and in the last sections of the chapter, we look at some of the more recent ideas in this field.

One recurring theme in this chapter is the need for adequate tools: most multidimensional visualization techniques are either not practical with paper and pencil, or are outright impossible without a computer (in particular when it comes to animated techniques). Moreover, as the number of variables increases, ...